Training in progress, epoch 1

config.json

@@ -1,13 +1,12 @@
 {
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "directionality": "bidi",
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "Financial",
     "1": "Arms",
@@ -21,7 +20,6 @@
     "9": "Porn"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "Arms": 1,
     "Crypto": 8,
@@ -34,22 +32,17 @@
     "Porn": 9,
     "Violence": 5
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.55.4",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 119547
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dae7fe89e09b084d77bddc1a58f308c1284fc018f9bdddafb55c4eb8462c730
-size 711468072
+oid sha256:69fc9ad03e2918e62cd8a3c308541b22c65bcc1bd84db2eb32b955bf6260137f
+size 267857176

tokenizer_config.json

@@ -43,7 +43,7 @@
   },
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
@@ -51,6 +51,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e7c97e419460649579447bee95bf6466bbf1c3fe56a621e291d5c9dd5d51c50
+oid sha256:a1b29786d57e85346b3bc20c1474f021b3664cb81de62db7159d49a809cbc133
 size 5713